Toward 3D avatar visualization of macedonian sign language

Abstract

Sign language is the first language of many people suffering hearing impairments. They learn it before getting their initial skills in writing or communicating through other methods. Written and auditory expressions are more difficult for users of sign languages. For them, the output should be presented in the form of gestures, facial expressions and body language. This paper presents a 3D visualization system that extensively uses animation and game concepts for accurately generating sign languages using 3D avatars. Every avatar is endowed with expressive range of gestures and anatomical features as subtle as muscles for mimicking the changes in facial expression. The platform works with transferring text into skeletal control parameters that are passed to the visualization engine. Transforms are calculated so the avatar rigging system can extensively utilize the skeletal and morph target controls for depicting visual signing.